More accurate tests for the statistical significance of result differences

Simple item page
dc.creatorYeh, Alexander
dc.date2000-08-08
dc.date.accessioned2026-07-07T03:16:26Z
dc.date.available2026-07-07T03:16:26Z
dc.descriptionStatistical significance testing of differences in values of metrics like recall, precision and balanced F-score is a necessary part of empirical natural language processing. Unfortunately, we find in a set of experiments that many commonly used tests often underestimate the significance and so are less likely to detect differences that exist between different techniques. This underestimation comes from an independence assumption that is often violated. We point out some useful tests that do not make this assumption, including computationally-intensive randomization tests.
dc.description7 pages, uses colacl.sty
dc.identifierhttps://arxiv.org/abs/cs/0008005
dc.identifierhttp://arxiv.org/abs/cs/0008005
dc.identifier18th International Conference on Computational Linguistics (COLING 2000), pages 947-953, Saarbruecken, Germany, July, 2000
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/30353
dc.subjectComputation and Language
dc.subjectI.2.7
dc.titleMore accurate tests for the statistical significance of result differences
dc.typetext

Files

Collections

arXiv